< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 8 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.8564. Min Act: -0.0000

Data Index: 1024447 (The Pile)

Max Activating Token Index: 474

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.4985. Min Act: -0.0000

Data Index: 1514834 (The Pile)

Max Activating Token Index: 866

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.1943. Min Act: -0.0000

Data Index: 1109776 (The Pile)

Max Activating Token Index: 111

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.1266. Min Act: -0.0000

Data Index: 239614 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.8564. Min Range: -3.8564

Max Act: 2.9226. Min Act: -0.0000

Data Index: 652627 (The Pile)

Max Activating Token Index: 324

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.0677. Min Act: -0.0000

Data Index: 479173 (The Pile)

Max Activating Token Index: 199

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.1126. Min Act: -0.0000

Data Index: 1146187 (The Pile)

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.1334. Min Act: -0.0000

Data Index: 882737 (The Pile)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.8564. Min Range: -3.8564

Max Act: 2.9360. Min Act: -0.0000

Data Index: 645139 (The Pile)

Max Activating Token Index: 682

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.8564. Min Range: -3.8564

Max Act: 2.9537. Min Act: -0.0000

Data Index: 93034 (The Pile)

Max Activating Token Index: 560

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.1179. Min Act: -0.0000

Data Index: 1069644 (The Pile)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.8564. Min Range: -3.8564

Max Act: 2.8511. Min Act: -0.0000

Data Index: 290202 (The Pile)

Max Activating Token Index: 571

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.8564. Min Range: -3.8564

Max Act: 3.0038. Min Act: -0.0000

Data Index: 849523 (The Pile)

Max Activating Token Index: 652

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.8564. Min Range: -3.8564

Max Act: 2.7304. Min Act: -0.0000

Data Index: 1073227 (The Pile)

Max Activating Token Index: 539

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.8564. Min Range: -3.8564

Max Act: 2.5978. Min Act: -0.0000

Data Index: 1119015 (The Pile)

Max Activating Token Index: 939

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.8564. Min Range: -3.8564

Max Act: 2.5629. Min Act: -0.0000

Data Index: 1707011 (The Pile)

Max Activating Token Index: 314

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.8564. Min Range: -3.8564

Max Act: 2.7187. Min Act: -0.0000

Data Index: 1626634 (The Pile)

Max Activating Token Index: 1010

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.8564. Min Range: -3.8564

Max Act: 2.5598. Min Act: -0.0000

Data Index: 1915948 (The Pile)

Max Activating Token Index: 554

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.8564. Min Range: -3.8564

Max Act: 2.6976. Min Act: -0.0000

Data Index: 1819428 (The Pile)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.8564. Min Range: -3.8564

Max Act: 2.5332. Min Act: -0.0000

Data Index: 738505 (The Pile)

Max Activating Token Index: 289

Click toggle to see full text

Truncated

Full Text #19